Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support

• URL: http://arxiv.org/abs/2507.13937v1
• Date: Fri, 18 Jul 2025 14:09:45 GMT
• Title: Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support
• Authors: Jan Trienes, Anastasiia Derzhanskaia, Roland Schwarzkopf, Markus Mühling, Jörg Schlötterer, Christin Seifert,
• Abstract summary: The system aims to provide fast and personalized responses, while reducing workload of university staff.<n>We employ retrieval-augmented generation to ground answers in university resources and to provide users with verifiable, contextually relevant information.
• Score: 2.1763238176533037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Marcel, a lightweight and open-source conversational agent designed to support prospective students with admission-related inquiries. The system aims to provide fast and personalized responses, while reducing workload of university staff. We employ retrieval-augmented generation to ground answers in university resources and to provide users with verifiable, contextually relevant information. To improve retrieval quality, we introduce an FAQ retriever that maps user questions to knowledge-base entries, allowing administrators to steer retrieval, and improving over standard dense/hybrid retrieval strategies. The system is engineered for easy deployment in resource-constrained academic settings. We detail the system architecture, provide a technical evaluation of its components, and report insights from a real-world deployment.

Related papers

• Machine Assistant with Reliable Knowledge: Enhancing Student Learning via RAG-based Retrieval [0.0]
  Machine Assistant with Reliable Knowledge (MARK) is a retrieval-augmented question-answering system designed to support student learning.<n>System is built on a retrieval-augmented generation (RAG) framework, which integrates a curated knowledge base to ensure factual consistency.
  arXiv  Detail & Related papers  (2025-06-28T22:17:27Z)
• ALOHA: Empowering Multilingual Agent for University Orientation with Hierarchical Retrieval [7.016945185385475]
  We introduce ALOHA, a multilingual agent enhanced by hierarchical retrieval for university orientation.<n>The system has been deployed and has provided service for more than 12,000 people.
  arXiv  Detail & Related papers  (2025-05-13T00:01:03Z)
• CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval [52.134133938779776]
  We present CLARINET, a system that asks informative clarification questions by choosing questions whose answers would maximize certainty in the correct candidate. Our approach works by augmenting a large language model (LLM) to condition on a retrieval distribution, finetuning end-to-end to generate the question that would have maximized the rank of the true candidate at each turn.
  arXiv  Detail & Related papers  (2024-04-28T18:21:31Z)
• STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases [93.96463520716759]
  We develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Knowledge Bases. Our benchmark covers three domains: product search, academic paper search, and queries in precision medicine. We design a novel pipeline to synthesize realistic user queries that integrate diverse relational information and complex textual properties.
  arXiv  Detail & Related papers  (2024-04-19T22:54:54Z)
• A large language model-assisted education tool to provide feedback on open-ended responses [2.624902795082451]
  We present a tool that uses large language models (LLMs), guided by instructor-defined criteria, to automate responses to open-ended questions. Our tool delivers rapid personalized feedback, enabling students to quickly test their knowledge and identify areas for improvement.
  arXiv  Detail & Related papers  (2023-07-25T19:49:55Z)
• Synergistic Interplay between Search and Large Language Models for Information Retrieval [141.18083677333848]
  InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections. InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-12T11:58:15Z)
• Retrieval Augmented Visual Question Answering with Outside Knowledge [14.371342370460685]
  Outside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQA task that requires retrieval of external knowledge to answer questions about images. Recent OK-VQA systems use Dense Passage Retrieval (DPR) to retrieve documents from external knowledge bases, such as Wikipedia, but with DPR trained separately from answer generation. We propose a joint training scheme which includes differentiable DPR integrated with answer generation so that the system can be trained in an end-to-end fashion.
  arXiv  Detail & Related papers  (2022-10-07T20:35:58Z)
• What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys [63.51903260461746]
  We propose a novel task for knowledge-driven follow-up question generation in conversational surveys. We constructed a new human-annotated dataset of human-written follow-up questions with dialogue history and labeled knowledge. We then propose a two-staged knowledge-driven model for the task, which generates informative and coherent follow-up questions.
  arXiv  Detail & Related papers  (2022-05-23T00:57:33Z)
• Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language [121.56329458876655]
  We introduce two new environments: the grid-world-based Q-BabyAI and the text-based Q-TextWorld. We propose the "Asking for Knowledge" (AFK) agent, which learns to generate language commands to query for meaningful knowledge.
  arXiv  Detail & Related papers  (2022-05-12T14:20:31Z)
• OpenQA: Hybrid QA System Relying on Structured Knowledge Base as well as Non-structured Data [15.585969737147892]
  We propose an intelligent question-answering system based on structured KB and unstructured data, called OpenQA. We integrate KBQA structured question answering based on semantic parsing and deep representation learning, and two-stage unstructured question answering based on retrieval and neural machine reading comprehension into OpenQA.
  arXiv  Detail & Related papers  (2021-12-31T09:15:39Z)
• Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning [56.771557756836906]
  We present a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision. Our system leads to state-of-the-art performance on a large-scale task for complex question answering over knowledge bases.
  arXiv  Detail & Related papers  (2020-10-29T18:28:16Z)
• Open-Retrieval Conversational Question Answering [62.11228261293487]
  We introduce an open-retrieval conversational question answering (ORConvQA) setting, where we learn to retrieve evidence from a large collection before extracting answers. We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.
  arXiv  Detail & Related papers  (2020-05-22T19:39:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.